使用pathlib在Python 3.6上工作的解决方案。

from pathlib import Path

sum([f.stat().st_size for f in Path("path").glob("**/*")])

我使用带有scandir的python 2.7.13，这里是我的一行递归函数，以获得文件夹的总大小:

from scandir import scandir
def getTotFldrSize(path):
    return sum([s.stat(follow_symlinks=False).st_size for s in scandir(path) if s.is_file(follow_symlinks=False)]) + \
    + sum([getTotFldrSize(s.path) for s in scandir(path) if s.is_dir(follow_symlinks=False)])

>>> print getTotFldrSize('.')
1203245680

https://pypi.python.org/pypi/scandir

这个脚本告诉您CWD中哪个文件最大，还告诉您文件在哪个文件夹中。 这个脚本适用于win8和python 3.3.3 shell

import os

folder=os.cwd()

number=0
string=""

for root, dirs, files in os.walk(folder):
    for file in files:
        pathname=os.path.join(root,file)
##        print (pathname)
##        print (os.path.getsize(pathname)/1024/1024)
        if number < os.path.getsize(pathname):
            number = os.path.getsize(pathname)
            string=pathname


##        print ()


print (string)
print ()
print (number)
print ("Number in bytes")

使用pathlib，我想出了这个一行程序来获取文件夹的大小:

sum(file.stat().st_size for file in Path(folder).rglob('*'))

这是我为一个漂亮的格式化输出:

from pathlib import Path


def get_folder_size(folder):
    return ByteSize(sum(file.stat().st_size for file in Path(folder).rglob('*')))


class ByteSize(int):

    _KB = 1024
    _suffixes = 'B', 'KB', 'MB', 'GB', 'PB'

    def __new__(cls, *args, **kwargs):
        return super().__new__(cls, *args, **kwargs)

    def __init__(self, *args, **kwargs):
        self.bytes = self.B = int(self)
        self.kilobytes = self.KB = self / self._KB**1
        self.megabytes = self.MB = self / self._KB**2
        self.gigabytes = self.GB = self / self._KB**3
        self.petabytes = self.PB = self / self._KB**4
        *suffixes, last = self._suffixes
        suffix = next((
            suffix
            for suffix in suffixes
            if 1 < getattr(self, suffix) < self._KB
        ), last)
        self.readable = suffix, getattr(self, suffix)

        super().__init__()

    def __str__(self):
        return self.__format__('.2f')

    def __repr__(self):
        return '{}({})'.format(self.__class__.__name__, super().__repr__())

    def __format__(self, format_spec):
        suffix, val = self.readable
        return '{val:{fmt}} {suf}'.format(val=val, fmt=format_spec, suf=suffix)

    def __sub__(self, other):
        return self.__class__(super().__sub__(other))

    def __add__(self, other):
        return self.__class__(super().__add__(other))
    
    def __mul__(self, other):
        return self.__class__(super().__mul__(other))

    def __rsub__(self, other):
        return self.__class__(super().__sub__(other))

    def __radd__(self, other):
        return self.__class__(super().__add__(other))
    
    def __rmul__(self, other):
        return self.__class__(super().__rmul__(other))   

用法:

>>> size = get_folder_size("c:/users/tdavis/downloads")
>>> print(size)
5.81 GB
>>> size.GB
5.810891855508089
>>> size.gigabytes
5.810891855508089
>>> size.PB
0.005674699077644618
>>> size.MB
5950.353260040283
>>> size
ByteSize(6239397620)

我还遇到了这个问题，它有一些更紧凑、可能更高效的打印文件大小的策略。

Du默认情况下不遵循符号链接。这里没有答案，使用follow_symlinks=False。

下面是一个遵循du默认行为的实现:

def du(path) -> int:
    total = 0
    for entry in os.scandir(path):
        if entry.is_file(follow_symlinks=False):
            total += entry.stat().st_size
        elif entry.is_dir(follow_symlinks=False):
            total += du(entry.path)
    return total

测试:

class Test(unittest.TestCase):
    def test_du(self):
        root = '/tmp/du_test'
        subprocess.run(['rm', '-rf', root])
        test_utils.mkdir(root)
        test_utils.create_file(root, 'A', '1M')
        test_utils.create_file(root, 'B', '1M')
        sub = '/'.join([root, 'sub'])
        test_utils.mkdir(sub)
        test_utils.create_file(sub, 'C', '1M')
        test_utils.create_file(sub, 'D', '1M')
        subprocess.run(['ln', '-s', '/tmp', '/'.join([root, 'link']), ])
        self.assertEqual(4 << 20, util.du(root))

我在这里有点晚(和新)，但我选择使用subprocess模块和Linux中的'du'命令行来检索文件夹大小的准确值，单位为MB。我必须使用if和elif用于根文件夹，否则子进程会由于返回的非零值而引发错误。

import subprocess
import os

#
# get folder size
#
def get_size(self, path):
    if os.path.exists(path) and path != '/':
        cmd = str(subprocess.check_output(['sudo', 'du', '-s', path])).\
            replace('b\'', '').replace('\'', '').split('\\t')[0]
        return float(cmd) / 1000000
    elif os.path.exists(path) and path == '/':
        cmd = str(subprocess.getoutput(['sudo du -s /'])). \
            replace('b\'', '').replace('\'', '').split('\n')
        val = cmd[len(cmd) - 1].replace('/', '').replace(' ', '')
        return float(val) / 1000000
    else: raise ValueError